R Notebook

if(!require("plotly")) {install.packages("plotly")}

Loading required package: plotly
Loading required package: ggplot2
Find out what's changed in ggplot2 at https://github.com/tidyverse/ggplot2/releases.

Attaching package: ‘plotly’

The following object is masked from ‘package:ggplot2’:

    last_plot

The following object is masked from ‘package:stats’:

    filter

The following object is masked from ‘package:graphics’:

    layout

# install.packages("latex2exp")
# install.packages("BiocManager") 
# install.packages("corrplot")
# BiocManager::install("EBImage")

if(!require("lme4")){install.packages("lme4")}

Loading required package: lme4
Loading required package: Matrix

if(!require("lmerTest")){install.packages("lmerTest")}

Loading required package: lmerTest

Attaching package: ‘lmerTest’

The following object is masked from ‘package:lme4’:

    lmer

The following object is masked from ‘package:stats’:

    step

if(!require("nlme")){install.packages("nlme")}

Loading required package: nlme

Attaching package: ‘nlme’

The following object is masked from ‘package:lme4’:

    lmList

if(!require("formattable")){install.packages("formattable")}

Loading required package: formattable

Attaching package: ‘formattable’

The following object is masked from ‘package:plotly’:

    style

if(!require("xgboost")){install.packages("xgboost")}

Loading required package: xgboost

Attaching package: ‘xgboost’

The following object is masked from ‘package:plotly’:

    slice

if(!require("processx")) {install.packages("processx")}

Loading required package: processx

if(!require("mefa")){install.packages("mefa")}

Loading required package: mefa
mefa 3.2-7   2016-01-11

library(plotly)
library(lme4)
library(lmerTest)
library(nlme)
library(formattable)
library(xgboost)

### Load libraries
library(EBImage)

Attaching package: ‘EBImage’

The following object is masked from ‘package:plotly’:

    toRGB

library(ggplot2)
library(stringr)
library(gridExtra)

Attaching package: ‘gridExtra’

The following object is masked from ‘package:EBImage’:

    combine

library(latex2exp)

Attaching package: ‘latex2exp’

The following object is masked from ‘package:plotly’:

    TeX

packageVersion('plotly')

[1] ‘4.9.1’

Sys.setenv("plotly_username"="thuynh32")
Sys.setenv("plotly_api_key"="xcSv1yzujDc1IGEwQlr2")

drive1 <- read.csv('../../../data/TT1/preprocessed/Analysis/TT1_Drive_1_PP.csv')
drive2 <- read.csv('../../../data/TT1/preprocessed/Analysis/TT1_Drive_2_PP.csv')
drive3 <- read.csv('../../../data/TT1/preprocessed/Analysis/TT1_Drive_3_PP.csv')
drive4 <- read.csv('../../../data/TT1/preprocessed/Analysis/TT1_Drive_4_PP.csv', stringsAsFactors = T)

combinedDf <- cbind(drive4, 
                    drive2$MeanPP_SegMax, drive3$MeanPP_SegMax, 
                    drive1$MeanPP_Seg0, drive2$MeanPP_Seg0, drive3$MeanPP_Seg0,
                    drive2$StdPP, drive3$StdPP 
                  )
names(combinedDf) <- c(names(drive4), "PP_Dev_2_Straight", "PP_Dev_3_Straight", "PP_Dev_1_Turning", "PP_Dev_2_Turning", "PP_Dev_3_Turning", "Std_PP_2", "Std_PP_3")

combinedDf$Subject <- paste0("#", str_pad(combinedDf$Subject, 2, pad="0"))

combinedDf_NoStressor <- combinedDf[combinedDf$Activity == "NO",]
combinedDf_Cognitive <- combinedDf[combinedDf$Activity == "C",]
combinedDf_Motoric <- combinedDf[combinedDf$Activity == "M",]

combinedDf_NoStressor$Subject <- as.factor(combinedDf_NoStressor$Subject)
combinedDf_Cognitive$Subject <- as.factor(combinedDf_Cognitive$Subject)
combinedDf_Motoric$Subject <- as.factor(combinedDf_Motoric$Subject)

COLOR_NORMAL <- list(color='rgb(120,120,120)')
COLOR_COGNITIVE <- list(color='rgb(158,202,225)')
COLOR_MOTORIC <- list(color='rgb(58,200,225)')
COLOR_FAILURE <- list(color='red')

yAxis <- list(
  title = 'Perinasal Perspiration (Log)',
  range=c(-0.3, 0.5)
)

THRESHOLD_MILD = 0.07
THRESHOLD_EXTREME = 0.2

MARKER_LINE_MILD = list(color="blue")
MARKER_LINE_EXTREME = list(color="red")

fig_NoStressor <- plot_ly(combinedDf_NoStressor, x = ~Subject, y = ~PP_Dev_2_Straight, type = 'bar', name = 'Cognitive - Mean PP (Straight)', marker=COLOR_COGNITIVE) %>%
  add_trace(y = ~PP_Dev_3_Straight, name = 'Motoric - Mean PP (Straight)', marker=COLOR_MOTORIC) %>% 
  add_trace(y = ~PP_Dev_2_Turning, name = 'Cognitive - Mean PP (Turning)', marker=COLOR_COGNITIVE) %>% 
  add_trace(y = ~PP_Dev_3_Turning, name = 'Motoric - Mean PP (Turning)', marker=COLOR_MOTORIC) %>% 
  add_trace(y = ~PP_Dev, name = 'Failure - PP Deviation', marker=COLOR_FAILURE) %>% 
  add_segments(x="#01", xend="#41", y = THRESHOLD_MILD, yend = THRESHOLD_MILD, name="Threshold: Mild Change of PP",
                           line=list(color="blue", dash = 'dot')) %>%
  # add_segments(x="#01", xend="#41", y = THRESHOLD_EXTREME, yend = THRESHOLD_EXTREME, name="Threshold: Extreme Change of PP",
  #                          line=list(color="darkred", dash = 'dot')) %>%
  layout(yaxis = yAxis, barmode = 'group', title="Failure Driving \n Group=No Stressor")

htmltools::tagList(fig_NoStressor)

A marker object has been specified, but markers is not in the mode
Adding markers to the mode...
A marker object has been specified, but markers is not in the mode
Adding markers to the mode...

fig_Cognitive <- plot_ly(combinedDf_Cognitive, x = ~Subject, y = ~PP_Dev_2_Straight, type = 'bar', name = 'Cognitive - Mean PP (Straight)', marker=COLOR_COGNITIVE) %>%
  add_trace(y = ~PP_Dev_3_Straight, name = 'Motoric - Mean PP (Straight)', marker=COLOR_MOTORIC) %>% 
  add_trace(y = ~PP_Dev_2_Turning, name = 'Cognitive - Mean PP (Turning)', marker=COLOR_COGNITIVE) %>% 
  add_trace(y = ~PP_Dev_3_Turning, name = 'Motoric - Mean PP (Turning)', marker=COLOR_MOTORIC) %>% 
  add_trace(y = ~PP_Dev, name = 'Failure - PP Deviation', marker=COLOR_FAILURE) %>% 
  add_segments(x="#02", xend="#22", y = THRESHOLD_MILD, yend = THRESHOLD_MILD, name="Threshold: Mild Change of PP",
                           line=list(color="blue", dash = 'dot')) %>%
  # add_segments(x="#02", xend="#22", y = THRESHOLD_EXTREME, yend = THRESHOLD_EXTREME, name="Threshold: Extreme Change of PP",
  #                          line=list(color="darkred", dash = 'dot')) %>%
  layout(yaxis = yAxis, barmode = 'group', title="Failure Driving \n Group=Cognitive")

htmltools::tagList(fig_Cognitive)

A marker object has been specified, but markers is not in the mode
Adding markers to the mode...
A marker object has been specified, but markers is not in the mode
Adding markers to the mode...

fig_Motoric <- plot_ly(combinedDf_Motoric, x = ~Subject, y = ~PP_Dev_2_Straight, type = 'bar', name = 'Cognitive - Mean PP (Straight)', marker=COLOR_COGNITIVE) %>%
  add_trace(y = ~PP_Dev_3_Straight, name = 'Motoric - Mean PP (Straight)', marker=COLOR_MOTORIC) %>% 
  add_trace(y = ~PP_Dev_2_Turning, name = 'Cognitive - Mean PP (Turning)', marker=COLOR_COGNITIVE) %>% 
  add_trace(y = ~PP_Dev_3_Turning, name = 'Motoric - Mean PP (Turning)', marker=COLOR_MOTORIC) %>% 
  add_trace(y = ~PP_Dev, name = 'Failure - PP Deviation', marker=COLOR_FAILURE) %>% 
  add_segments(x="#05", xend="#31", y = THRESHOLD_MILD, yend = THRESHOLD_MILD, name="Threshold: Mild Change of PP",
                           line=list(color="blue", dash = 'dot')) %>%
  # add_segments(x="#05", xend="#31", y = THRESHOLD_EXTREME, yend = THRESHOLD_EXTREME, name="Threshold: Extreme Change of PP",
  #                          line=list(color="darkred", dash = 'dot')) %>%
  layout(yaxis = yAxis, barmode = 'group', title="Failure Driving \n Group: Motoric")

htmltools::tagList(fig_Motoric)

A marker object has been specified, but markers is not in the mode
Adding markers to the mode...
A marker object has been specified, but markers is not in the mode
Adding markers to the mode...

library(nlme)

combinedDf$Subject = as.factor(combinedDf$Subject)
combinedDf$Activity = as.factor(combinedDf$Activity)

combinedDf$PP_Dev_Group = ifelse(combinedDf$PP_Dev > THRESHOLD_MILD, 1, 0)

model = lme(PP_Dev ~ 
              abs(PP_Dev_2_Straight)
              + abs(PP_Dev_3_Straight)
              + abs(PP_Dev_2_Turning) 
              + abs(PP_Dev_3_Turning)
              + factor(Activity), 
            random=~1|Subject,
            data=combinedDf,
            method="REML")

# anova(model)
summary(model)

Linear mixed-effects model fit by REML
 Data: combinedDf 

Random effects:
 Formula: ~1 | Subject
        (Intercept)   Residual
StdDev:  0.07501618 0.02813106

Fixed effects: PP_Dev ~ abs(PP_Dev_2_Straight) + abs(PP_Dev_3_Straight) + abs(PP_Dev_2_Turning) +      abs(PP_Dev_3_Turning) + factor(Activity) 

 Correlation: 
                       (Intr) a(PP_D_2_S a(PP_D_3_S a(PP_D_2_T a(PP_D_3_T fc(A)M
abs(PP_Dev_2_Straight)  0.598                                                   
abs(PP_Dev_3_Straight)  0.082  0.028                                            
abs(PP_Dev_2_Turning)  -0.508 -0.715     -0.483                                 
abs(PP_Dev_3_Turning)  -0.586 -0.456     -0.706      0.529                      
factor(Activity)M      -0.385 -0.171      0.355     -0.181     -0.125           
factor(Activity)NO     -0.154  0.026      0.547     -0.450     -0.368      0.616

Standardized Within-Group Residuals:
         Min           Q1          Med           Q3          Max 
-0.440076168 -0.154672364 -0.002413178  0.107752315  0.674410551 

Number of Observations: 21
Number of Groups: 21 

plot(model)

model = lme(PP_Dev ~ 
              abs(PP_Dev_2_Turning)
              + factor(Activity), 
            random=~1|Subject,
            data=combinedDf,
            method="REML")

# anova(model)
summary(model)

Linear mixed-effects model fit by REML
 Data: combinedDf 

Random effects:
 Formula: ~1 | Subject
        (Intercept) Residual
StdDev:  0.08150667 0.030565

Fixed effects: PP_Dev ~ abs(PP_Dev_2_Turning) + factor(Activity) 

 Correlation: 
                      (Intr) a(PP_D fc(A)M
abs(PP_Dev_2_Turning) -0.497              
factor(Activity)M     -0.457 -0.270       
factor(Activity)NO    -0.346 -0.423  0.550

Standardized Within-Group Residuals:
        Min          Q1         Med          Q3         Max 
-0.49096784 -0.21744976  0.01851302  0.20552883  0.50745083 

Number of Observations: 21
Number of Groups: 21 

plot(model)

model = lme(PP_Dev ~ 
              PP_Dev_2_Straight + 
              PP_Dev_3_Straight + 
              PP_Dev_1_Turning + 
              PP_Dev_2_Turning + 
              PP_Dev_3_Turning + 
              Std_PP_2 + 
              Std_PP_3 +
              factor(Activity), 
            random=~1|Subject,
            data=combinedDf,
            method="REML")

# anova(model)
summary(model)

Linear mixed-effects model fit by REML
 Data: combinedDf 

Random effects:
 Formula: ~1 | Subject
        (Intercept)   Residual
StdDev:  0.08634381 0.03237893

Fixed effects: PP_Dev ~ PP_Dev_2_Straight + PP_Dev_3_Straight + PP_Dev_1_Turning +      PP_Dev_2_Turning + PP_Dev_3_Turning + Std_PP_2 + Std_PP_3 +      factor(Activity) 

 Correlation: 
                   (Intr) PP_D_2_S PP_D_3_S PP_D_1 PP_D_2_T PP_D_3_T S_PP_2 S_PP_3 fc(A)M
PP_Dev_2_Straight  -0.056                                                                
PP_Dev_3_Straight   0.048 -0.363                                                         
PP_Dev_1_Turning   -0.797  0.130    0.176                                                
PP_Dev_2_Turning    0.360 -0.754    0.023   -0.422                                       
PP_Dev_3_Turning   -0.140  0.268   -0.700   -0.283 -0.252                                
Std_PP_2            0.199 -0.570   -0.066   -0.333  0.816   -0.134                       
Std_PP_3           -0.818  0.423   -0.201    0.672 -0.688    0.275   -0.604              
factor(Activity)M   0.162 -0.317    0.495   -0.054  0.166   -0.372    0.128 -0.430       
factor(Activity)NO -0.228 -0.225    0.426    0.191 -0.123   -0.235   -0.263  0.124  0.481

Standardized Within-Group Residuals:
        Min          Q1         Med          Q3         Max 
-0.48616985 -0.10946874 -0.02066106  0.16055277  0.56942657 

Number of Observations: 21
Number of Groups: 21 

plot(model)

combinedDf$PP_Dev <- NULL

combinedDf$Subject <- NULL
combinedDf$Activity_NO <- ifelse(combinedDf$Activity == "NO", 1, 0)
combinedDf$Activity_C <- ifelse(combinedDf$Activity == "C", 1, 0)
combinedDf$Activity_M <- ifelse(combinedDf$Activity == "M", 1, 0)
combinedDf$Activity <- NULL

combinedDf$Class <- ifelse(combinedDf$PP_Dev_Group == 1, T, F)
combinedDf$PP_Dev_Group <- NULL

# library(mefa)
# combinedDf <- rep(combinedDf, 10) 

# s=55, f=4

set.seed(5151) 
n_folds <- 3
params <- param <- list(objective       = "binary:logistic", 
               booster          = "gbtree",
               eval_metric      = "auc",
               eta              = 0.1,
               max_depth        = 8,
               alpha            = 1,
               lambda           = 0,
               gamma            = 0.3,
               min_child_weight = 0.3,
               subsample        = 1,
               colsample_bytree = 0.5)
           
# xgb_m <- xgb.cv(   params               = param,
#                   data = as.matrix(combinedDf %>% select(-Class)) ,
#                   label =  combinedDf$Class,
#                   nrounds             = 100,
#                   verbose             = F,
#                   prediction          = T,
#                   maximize            = T,
#                   nfold = n_folds,
#                   metrics  = "auc",
#                   early_stopping_rounds = 100,
#                   stratified       = F,
#                   scale_pos_weight = 0.5)
# 
# # xgb_m$evaluation_log[xgb_m$best_iteration,"test_auc_mean"]
# xgb_m$evaluation_log[xgb_m$best_iteration,]

# Error         
xgb_m <- xgb.cv(   params               = param,
                  data = as.matrix(combinedDf %>% select(-Class)) ,
                  label =  combinedDf$Class,
                  nrounds             = 500,
                  verbose             = F,
                  prediction          = T,
                  maximize            = T,
                  nfold               = n_folds,
                  metrics             = c("auc", "error"),
                  early_stopping_rounds = 100,
                  stratified            = F,
                  scale_pos_weight      = 3.05)

# xgb_m$evaluation_log[xgb_m$best_iteration,"test_auc_mean"]
xgb_m$evaluation_log[xgb_m$best_iteration,]

NA

library(pROC)

# it = which.max(xgb_m$evaluation_log$test_auc_mean)
# best.iter = xgb_m$evaluation_log$iter[it]
# best.iter 

plot(pROC::roc(response = ifelse(combinedDf$Class==T, 1, 0),
               predictor = xgb_m$pred,
               levels=c(0, 1)),
     lwd=1.5) 

Setting direction: controls < cases